DocumentationWorkflowsAI and agents
Agent node
Runs one of your personal agents - with its persona, its memory and its workspace folder as its workbench. Learn how to configure it, map inputs and outputs, run a test and resolve common errors.
8 min readUpdated
What this node does
Runs one of your personal agents - with its persona, its memory and its workspace folder as its workbench.
Use Agent as a clearly defined step in an anymize workflow.
- Processes one input.
- Provides one output for following steps.
- Can call approved tool nodes autonomously.
Set up the node
- 01Open a workflow and add Agent from the node catalog.
- 02Complete the required fields and map values from previous steps.
- 03Run the node with a small test record and inspect its output.
- 04Connect the successful output and activate the workflow after an end-to-end test.
Operations and modes
Agent has one focused purpose. Its available settings appear when you select the node.
Settings
| Field | Meaning | Area |
|---|---|---|
| Maximum reasoning steps | Maximum model rounds (1 to 25). Each round can call several tools. The run fails if the agent does not produce a final answer. | Standard |
| Credit budget | Stops further model and tool calls at this usage (1 to 100000 credits). A model call already in progress can exceed the budget. | Standard |
| Maximum tool calls | Limits each agent step to 1 to 100 tool calls, including multiple calls requested in a single model round. | Standard |
| Agent | Which of your agents runs the brief. | Standard |
| Brief (required) | Free text or a variable like {{ $json.message }}. | Standard |
| Model fallback | Only used when the agent itself has no model set. | Standard |
| Output format | Enforce JSON for downstream nodes. | Standard |
| JSON structure (optional) | Example with field names and types; leave empty to keep the structure free. | Standard |
Inputs and outputs
| Input | Meaning | Type |
|---|---|---|
| user prompt | The brief for the agent. Overrides the inline brief field. | text |
| Output | Meaning | Type |
|---|---|---|
| output | The agent's answer (final assistant message). | text |
| steps | All tool calls + results of the run. | json |
Example and test run
Brief an agent: begin with a small, recognizable record. Inspect the output and only map fields that are present there.
Test-run example
{
"userPrompt": "Sichte die Notizen in deinem Arbeitsordner und fasse den aktuellen Stand in drei Sätzen zusammen."
}Access and security
Before activation, review which data enters this step and what its output contains.
Store keys and credentials in the protected connection manager. Never paste them into normal workflow fields, test data or descriptions.
Troubleshooting
- No output: inspect the latest run and confirm that the previous node returned the expected fields.
- Empty variable: open the previous step output and use a field name from the real test data.